© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 24178
    Prev
    Next
    INDEX
    Explanations

    strongly negative adjectives

    oai_token-act-pair · gpt-3.5-turbo

    negative assessments or critiques, particularly the word "terrible."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.94
    pai
    -0.94
    ilus
    -0.83
    ovember
    -0.78
    illary
    -0.78
    cript
    -0.77
    arger
    -0.76
    adr
    -0.76
    ioch
    -0.75
    RAFT
    -0.75
    POSITIVE LOGITS
     nightmare
    0.88
     earthqu
    0.88
     awful
    0.87
     havoc
    0.87
     horrible
    0.85
     nightmares
    0.83
     terrible
    0.83
     sounding
    0.82
     headache
    0.81
     conflic
    0.77
    Activations Density 0.012%

    No Known Activations